A new method enables any-order generation in pretrained autoregressive image models, which are otherwise locked into a single fixed raster-scan factorization of the image distribution during training and therefore cannot inpaint, outpaint, or edit at inference time. The work targets the inflexibility that existing solutions have not resolved, though the source excerpt does not name the authors, institution, or a benchmark figure.
Autoregressive (AR) image generators are powerful in principle but inflexible in practice: training with a fixed raster-scan order hardcodes a single factorization of the image distribution into the model, leaving it unable to inpaint, outpaint, or edit at inference time. Existing solutions, includi
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.